{"list":"other","total":117,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1905.13260","title":"Large Scale Incremental Learning","created":"2019-05-30","cited_by_count":732},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"1807.09536","title":"End-to-End Incremental Learning","created":"2018-07-25","cited_by_count":597},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"1904.05046","title":"Generalizing from a Few Examples: A Survey on Few-Shot Learning","created":"2019-04-10","cited_by_count":463},{"id":"1807.01613","title":"Conditional Neural Processes","created":"2018-07-04","cited_by_count":426},{"id":"1804.09458","title":"Dynamic Few-Shot Visual Learning without Forgetting","created":"2018-04-25","cited_by_count":385},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1704.04394","title":"DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents","created":"2017-04-14","cited_by_count":310},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"2004.10956","title":"Few-Shot Class-Incremental Learning","created":"2020-04-23","cited_by_count":251},{"id":"1503.01817","title":"YFCC100M: The New Data in Multimedia Research","created":"2015-03-05","cited_by_count":235},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"2101.06395","title":"Free Lunch for Few-shot Learning: Distribution Calibration","created":"2021-01-16","cited_by_count":165},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","cited_by_count":163},{"id":"1902.09130","title":"An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition","created":"2019-02-25","cited_by_count":151},{"id":"1906.11415","title":"Few-Shot Video Classification via Temporal Alignment","created":"2019-06-27","cited_by_count":125},{"id":"1706.03466","title":"Few-Shot Image Recognition by Predicting Parameters from Activations","created":"2017-06-12","cited_by_count":122},{"id":"2003.04668","title":"Incremental Few-Shot Object Detection","created":"2020-03-10","cited_by_count":102},{"id":"2101.06184","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","created":"2021-01-15","cited_by_count":84},{"id":"1907.09021","title":"TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition","created":"2019-07-21","cited_by_count":71},{"id":"1804.08281","title":"Memory Matching Networks for One-Shot Image Recognition","created":"2018-04-23","cited_by_count":65},{"id":"2307.04722","title":"Advances and Challenges in Meta-Learning: A Technical Review","created":"2023-07-10","cited_by_count":65},{"id":"2103.14107","title":"Stepwise Goal-Driven Networks for Trajectory Prediction","created":"2021-03-25","cited_by_count":62},{"id":"1805.07513","title":"Diverse Few-Shot Text Classification with Multiple Metrics","created":"2018-05-19","cited_by_count":61},{"id":"2112.05132","title":"Spatio-temporal Relation Modeling for Few-shot Action Recognition","created":"2021-12-09","cited_by_count":53},{"id":"2010.08946","title":"Temporal Binary Representation for Event-Based Action Recognition","created":"2020-10-18","cited_by_count":51},{"id":"2005.13713","title":"Few-Shot Open-Set Recognition using Meta-Learning","created":"2020-05-27","cited_by_count":50},{"id":"2010.09982","title":"Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition","created":"2020-10-20","cited_by_count":50},{"id":"2204.13423","title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","created":"2022-04-28","cited_by_count":50},{"id":"2206.04006","title":"Few-Shot Audio-Visual Learning of Environment Acoustics","created":"2022-06-08","cited_by_count":48},{"id":"2203.08568","title":"In-Context Learning for Few-Shot Dialogue State Tracking","created":"2022-03-16","cited_by_count":47},{"id":"1909.07945","title":"ProtoGAN: Towards Few Shot Learning for Action Recognition","created":"2019-09-17","cited_by_count":41},{"id":"2303.02982","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","created":"2023-03-06","cited_by_count":41},{"id":"1801.09086","title":"A Generative Approach to Zero-Shot and Few-Shot Action Recognition","created":"2018-01-27","cited_by_count":39},{"id":"1904.08479","title":"An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning","created":"2019-04-17","cited_by_count":38},{"id":"2304.00946","title":"MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition","created":"2023-04-03","cited_by_count":37},{"id":"2107.04782","title":"TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition","created":"2021-07-10","cited_by_count":35},{"id":"2207.05515","title":"Compound Prototype Matching for Few-shot Action Recognition","created":"2022-07-12","cited_by_count":35},{"id":"2308.03063","title":"M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition","created":"2023-08-06","cited_by_count":34},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29},{"id":"2101.08085","title":"Few-shot Action Recognition with Prototype-centered Attentive Learning","created":"2021-01-20","cited_by_count":28},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28},{"id":"2105.04823","title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","created":"2021-05-11","cited_by_count":27},{"id":"2303.07502","title":"Meta-learning approaches for few-shot learning: A survey of recent advances","created":"2023-03-13","cited_by_count":25},{"id":"2405.02077","title":"MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition","created":"2024-05-03","cited_by_count":25},{"id":"2308.09346","title":"Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching","created":"2023-08-18","cited_by_count":24},{"id":"2012.13823","title":"Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition","created":"2020-12-26","cited_by_count":23},{"id":"2105.08149","title":"Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments","created":"2021-05-17","cited_by_count":23},{"id":"2207.10785","title":"Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments","created":"2022-07-21","cited_by_count":23},{"id":"2210.16820","title":"Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition","created":"2022-10-30","cited_by_count":22},{"id":"1810.04511","title":"Interpretable Spatio-temporal Attention for Video Action Recognition","created":"2018-10-01","cited_by_count":20},{"id":"1909.06423","title":"Zero-Shot Action Recognition in Videos: A Survey","created":"2019-09-13","cited_by_count":19},{"id":"2010.06215","title":"Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization","created":"2020-10-13","cited_by_count":18},{"id":"2308.04828","title":"Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning","created":"2023-08-09","cited_by_count":16},{"id":"2102.08997","title":"One-shot action recognition in challenging therapy scenarios","created":"2021-02-17","cited_by_count":15},{"id":"2111.04316","title":"SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning","created":"2021-11-08","cited_by_count":15},{"id":"2112.01037","title":"Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention","created":"2021-12-02","cited_by_count":15},{"id":"2301.07944","title":"Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition","created":"2023-01-19","cited_by_count":15},{"id":"1810.08691","title":"Audio-Based Activities of Daily Living (ADL) Recognition with Large-Scale Acoustic Embeddings from Online Videos","created":"2018-10-19","cited_by_count":13},{"id":"2212.04873","title":"Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition","created":"2022-12-09","cited_by_count":13},{"id":"2309.03989","title":"CDFSL-V: Cross-Domain Few-Shot Learning for Videos","created":"2023-09-07","cited_by_count":13},{"id":"2201.05916","title":"Multi-level Second-order Few-shot Learning","created":"2022-01-15","cited_by_count":12},{"id":"2301.03330","title":"HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition","created":"2023-01-09","cited_by_count":12},{"id":"2303.09756","title":"Video Action Recognition with Attentive Semantic Units","created":"2023-03-17","cited_by_count":12},{"id":"2307.07286","title":"One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching","created":"2023-07-14","cited_by_count":12},{"id":"2109.15317","title":"Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation","created":"2021-09-30","cited_by_count":11},{"id":"2308.07119","title":"On the Importance of Spatial Relations for Few-shot Action Recognition","created":"2023-08-14","cited_by_count":11},{"id":"2208.09424","title":"Hierarchical Compositional Representations for Few-shot Action Recognition","created":"2022-08-19","cited_by_count":10}],"next_cursor":"100"}